初始化项目，由ModelHub XC社区提供模型

Model: fava-uw/fava-model Source: Original Platform
2026-05-14 03:47:45 +08:00
commit fe3ccbba57
32 changed files with 713 additions and 0 deletions
--- a/.gitattributes
+++ b/.gitattributes
@@ -0,0 +1,35 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text
--- a/README.md
+++ b/README.md
@@ -0,0 +1,26 @@
+---
+license: mit
+---
+FAVA, a verification model.
+
+```
+import torch
+import vllm
+from transformers import AutoTokenizer, AutoModelForSequenceClassification
+
+model = vllm.LLM(model="fava-uw/fava-model")
+sampling_params = vllm.SamplingParams(
+  temperature=0,
+  top_p=1.0,
+  max_tokens=1024,
+)
+
+INPUT = "Read the following references:\n{evidence}\nPlease identify all the errors in the following text using the information in the references provided and suggest edits if necessary:\n[Text] {output}\n[Edited] "
+
+output = "" # add your passage to verify
+evidence = "" # add a piece of evidence
+prompts = [INPUT.format_map({"evidence": evidence, "output": output})]
+outputs = model.generate(prompts, sampling_params)
+outputs = [it.outputs[0].text for it in outputs]
+print(outputs[0])
+```
--- a/added_tokens.json
+++ b/added_tokens.json
@@ -0,0 +1,3 @@
+{
+  "<pad>": 32000
+}
--- a/config.json
+++ b/config.json
@@ -0,0 +1,25 @@
+{
+  "_name_or_path": "meta-llama/Llama-2-7b-chat-hf",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 11008,
+  "max_position_embeddings": 4096,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 32,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.32.0.dev0",
+  "use_cache": true,
+  "vocab_size": 32001
+}
--- a/generation_config.json
+++ b/generation_config.json
@@ -0,0 +1,10 @@
+{
+  "bos_token_id": 1,
+  "do_sample": true,
+  "eos_token_id": 2,
+  "max_length": 4096,
+  "pad_token_id": 0,
+  "temperature": 0.6,
+  "top_p": 0.9,
+  "transformers_version": "4.32.0.dev0"
+}
--- a/open_instruct/1694454900.079274/events.out.tfevents.1694454900.g3073.19792.1
+++ b/open_instruct/1694454900.079274/events.out.tfevents.1694454900.g3073.19792.1
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a52b51160518605bb4a367c6663100c28cb9ea35173d3848304eea8e6c581565
+size 1831
--- a/open_instruct/1694454900.0843773/hparams.yml
+++ b/open_instruct/1694454900.0843773/hparams.yml
@@ -0,0 +1,32 @@
+checkpointing_steps: '50'
+config_name: null
+dataset_config_name: null
+dataset_name: null
+gradient_accumulation_steps: 16
+learning_rate: 2.0e-05
+logging_steps: 1
+lora_alpha: 16
+lora_dropout: 0.1
+lora_rank: 64
+low_cpu_mem_usage: false
+lr_scheduler_type: cosine
+max_seq_length: 2048
+max_train_steps: 550
+model_name_or_path: meta-llama/Llama-2-7b-chat-hf
+num_train_epochs: 2
+output_dir: multi_passage_w_qa
+overwrite_cache: false
+per_device_train_batch_size: 1
+preprocessing_num_workers: 16
+report_to: tensorboard
+resume_from_checkpoint: null
+save_merged_lora_model: false
+seed: null
+tokenizer_name: meta-llama/Llama-2-7b-chat-hf
+train_file: /gscratch/h2lab/abhikam/llm-factuality/data/training/open-instruct-multi-qa.json
+use_flash_attn: true
+use_lora: false
+use_slow_tokenizer: true
+warmup_ratio: 0.03
+weight_decay: 0.0
+with_tracking: true
--- a/open_instruct/1694473353.448148/events.out.tfevents.1694473353.g3057.74725.1
+++ b/open_instruct/1694473353.448148/events.out.tfevents.1694473353.g3057.74725.1
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8a416f1323b83ccf64cef4a6e5115f7fb5422fe96c7430351aad5d473f796c45
+size 1916
--- a/open_instruct/1694473353.4580002/hparams.yml
+++ b/open_instruct/1694473353.4580002/hparams.yml
@@ -0,0 +1,32 @@
+checkpointing_steps: '50'
+config_name: null
+dataset_config_name: null
+dataset_name: null
+gradient_accumulation_steps: 16
+learning_rate: 2.0e-05
+logging_steps: 1
+lora_alpha: 16
+lora_dropout: 0.1
+lora_rank: 64
+low_cpu_mem_usage: false
+lr_scheduler_type: cosine
+max_seq_length: 2048
+max_train_steps: 550
+model_name_or_path: meta-llama/Llama-2-7b-chat-hf
+num_train_epochs: 2
+output_dir: multi_passage_w_qa
+overwrite_cache: false
+per_device_train_batch_size: 1
+preprocessing_num_workers: 16
+report_to: tensorboard
+resume_from_checkpoint: multi_passage_w_qa/step_100
+save_merged_lora_model: false
+seed: null
+tokenizer_name: meta-llama/Llama-2-7b-chat-hf
+train_file: /gscratch/h2lab/abhikam/llm-factuality/data/training/open-instruct-multi-qa.json
+use_flash_attn: true
+use_lora: false
+use_slow_tokenizer: true
+warmup_ratio: 0.03
+weight_decay: 0.0
+with_tracking: true
--- a/open_instruct/1694473649.2233653/events.out.tfevents.1694473649.g3057.77254.1
+++ b/open_instruct/1694473649.2233653/events.out.tfevents.1694473649.g3057.77254.1
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:10b74c6f774d729b6af680f4e8ea767cfabf2df025cd74f71df9640b862dba10
+size 1916
--- a/open_instruct/1694473649.2345717/hparams.yml
+++ b/open_instruct/1694473649.2345717/hparams.yml
@@ -0,0 +1,32 @@
+checkpointing_steps: '50'
+config_name: null
+dataset_config_name: null
+dataset_name: null
+gradient_accumulation_steps: 16
+learning_rate: 2.0e-05
+logging_steps: 1
+lora_alpha: 16
+lora_dropout: 0.1
+lora_rank: 64
+low_cpu_mem_usage: false
+lr_scheduler_type: cosine
+max_seq_length: 2048
+max_train_steps: 550
+model_name_or_path: meta-llama/Llama-2-7b-chat-hf
+num_train_epochs: 2
+output_dir: multi_passage_w_qa
+overwrite_cache: false
+per_device_train_batch_size: 1
+preprocessing_num_workers: 16
+report_to: tensorboard
+resume_from_checkpoint: multi_passage_w_qa/step_100
+save_merged_lora_model: false
+seed: null
+tokenizer_name: meta-llama/Llama-2-7b-chat-hf
+train_file: /gscratch/h2lab/abhikam/llm-factuality/data/training/open-instruct-multi-qa.json
+use_flash_attn: true
+use_lora: false
+use_slow_tokenizer: true
+warmup_ratio: 0.03
+weight_decay: 0.0
+with_tracking: true
--- a/open_instruct/1694499102.1265042/events.out.tfevents.1694499102.g3041.70110.1
+++ b/open_instruct/1694499102.1265042/events.out.tfevents.1694499102.g3041.70110.1
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c6035e9cf6d2060a3a51c046446e92541d4b25a490c3bda38eb864b7ee1efbc9
+size 1916
--- a/open_instruct/1694499102.1359086/hparams.yml
+++ b/open_instruct/1694499102.1359086/hparams.yml
@@ -0,0 +1,32 @@
+checkpointing_steps: '50'
+config_name: null
+dataset_config_name: null
+dataset_name: null
+gradient_accumulation_steps: 16
+learning_rate: 2.0e-05
+logging_steps: 1
+lora_alpha: 16
+lora_dropout: 0.1
+lora_rank: 64
+low_cpu_mem_usage: false
+lr_scheduler_type: cosine
+max_seq_length: 2048
+max_train_steps: 550
+model_name_or_path: meta-llama/Llama-2-7b-chat-hf
+num_train_epochs: 2
+output_dir: multi_passage_w_qa
+overwrite_cache: false
+per_device_train_batch_size: 1
+preprocessing_num_workers: 16
+report_to: tensorboard
+resume_from_checkpoint: multi_passage_w_qa/step_250
+save_merged_lora_model: false
+seed: null
+tokenizer_name: meta-llama/Llama-2-7b-chat-hf
+train_file: /gscratch/h2lab/abhikam/llm-factuality/data/training/open-instruct-multi-qa.json
+use_flash_attn: true
+use_lora: false
+use_slow_tokenizer: true
+warmup_ratio: 0.03
+weight_decay: 0.0
+with_tracking: true
--- a/open_instruct/1694517340.2777019/events.out.tfevents.1694517340.g3043.20410.1
+++ b/open_instruct/1694517340.2777019/events.out.tfevents.1694517340.g3043.20410.1
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:52287e454a884daa449c4f4315dc8768890c0b0c5fdcfdd36f21a6d0026f475d
+size 1916
--- a/open_instruct/1694517340.3150113/hparams.yml
+++ b/open_instruct/1694517340.3150113/hparams.yml
@@ -0,0 +1,32 @@
+checkpointing_steps: '50'
+config_name: null
+dataset_config_name: null
+dataset_name: null
+gradient_accumulation_steps: 16
+learning_rate: 2.0e-05
+logging_steps: 1
+lora_alpha: 16
+lora_dropout: 0.1
+lora_rank: 64
+low_cpu_mem_usage: false
+lr_scheduler_type: cosine
+max_seq_length: 2048
+max_train_steps: 550
+model_name_or_path: meta-llama/Llama-2-7b-chat-hf
+num_train_epochs: 2
+output_dir: multi_passage_w_qa
+overwrite_cache: false
+per_device_train_batch_size: 1
+preprocessing_num_workers: 16
+report_to: tensorboard
+resume_from_checkpoint: multi_passage_w_qa/step_400
+save_merged_lora_model: false
+seed: null
+tokenizer_name: meta-llama/Llama-2-7b-chat-hf
+train_file: /gscratch/h2lab/abhikam/llm-factuality/data/training/open-instruct-multi-qa.json
+use_flash_attn: true
+use_lora: false
+use_slow_tokenizer: true
+warmup_ratio: 0.03
+weight_decay: 0.0
+with_tracking: true
--- a/open_instruct/1694518076.1833658/events.out.tfevents.1694518076.g3043.23771.1
+++ b/open_instruct/1694518076.1833658/events.out.tfevents.1694518076.g3043.23771.1
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e0f450f6e7e4caa1407a2ad7d4d1a601ae6946ebe59c4fe8b924b0ed56a0ecbd
+size 1916
--- a/open_instruct/1694518076.2119565/hparams.yml
+++ b/open_instruct/1694518076.2119565/hparams.yml
@@ -0,0 +1,32 @@
+checkpointing_steps: '50'
+config_name: null
+dataset_config_name: null
+dataset_name: null
+gradient_accumulation_steps: 16
+learning_rate: 2.0e-05
+logging_steps: 1
+lora_alpha: 16
+lora_dropout: 0.1
+lora_rank: 64
+low_cpu_mem_usage: false
+lr_scheduler_type: cosine
+max_seq_length: 2048
+max_train_steps: 550
+model_name_or_path: meta-llama/Llama-2-7b-chat-hf
+num_train_epochs: 2
+output_dir: multi_passage_w_qa
+overwrite_cache: false
+per_device_train_batch_size: 1
+preprocessing_num_workers: 16
+report_to: tensorboard
+resume_from_checkpoint: multi_passage_w_qa/step_400
+save_merged_lora_model: false
+seed: null
+tokenizer_name: meta-llama/Llama-2-7b-chat-hf
+train_file: /gscratch/h2lab/abhikam/llm-factuality/data/training/open-instruct-multi-qa.json
+use_flash_attn: true
+use_lora: false
+use_slow_tokenizer: true
+warmup_ratio: 0.03
+weight_decay: 0.0
+with_tracking: true
--- a/open_instruct/1694518380.1387873/events.out.tfevents.1694518380.g3043.25749.1
+++ b/open_instruct/1694518380.1387873/events.out.tfevents.1694518380.g3043.25749.1
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5338826a2287655b7c7a2d302534670ad3cad3742b52f3e4fee44f4fb3373397
+size 1916
--- a/open_instruct/1694518380.279593/hparams.yml
+++ b/open_instruct/1694518380.279593/hparams.yml
@@ -0,0 +1,32 @@
+checkpointing_steps: '50'
+config_name: null
+dataset_config_name: null
+dataset_name: null
+gradient_accumulation_steps: 16
+learning_rate: 2.0e-05
+logging_steps: 1
+lora_alpha: 16
+lora_dropout: 0.1
+lora_rank: 64
+low_cpu_mem_usage: false
+lr_scheduler_type: cosine
+max_seq_length: 2048
+max_train_steps: 550
+model_name_or_path: meta-llama/Llama-2-7b-chat-hf
+num_train_epochs: 2
+output_dir: multi_passage_w_qa
+overwrite_cache: false
+per_device_train_batch_size: 1
+preprocessing_num_workers: 16
+report_to: tensorboard
+resume_from_checkpoint: multi_passage_w_qa/step_400
+save_merged_lora_model: false
+seed: null
+tokenizer_name: meta-llama/Llama-2-7b-chat-hf
+train_file: /gscratch/h2lab/abhikam/llm-factuality/data/training/open-instruct-multi-qa.json
+use_flash_attn: true
+use_lora: false
+use_slow_tokenizer: true
+warmup_ratio: 0.03
+weight_decay: 0.0
+with_tracking: true
--- a/open_instruct/events.out.tfevents.1694454899.g3073.19792.0
+++ b/open_instruct/events.out.tfevents.1694454899.g3073.19792.0
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f78aadb6ad02755c808b0772534583a6ead1b5c08241a0cefca5b33f5b53b1f1
+size 14681
--- a/open_instruct/events.out.tfevents.1694473353.g3057.74725.0
+++ b/open_instruct/events.out.tfevents.1694473353.g3057.74725.0
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bf6c9632b71373703f0f87bdbdbe03c8c2112cc8e973a317cddffdfe014aa899
+size 290
--- a/open_instruct/events.out.tfevents.1694473649.g3057.77254.0
+++ b/open_instruct/events.out.tfevents.1694473649.g3057.77254.0
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5b89d08fd51bc5b219476775fc54aaf11dba1f43fe62b6e7c375dbef275780b7
+size 19325
--- a/open_instruct/events.out.tfevents.1694499102.g3041.70110.0
+++ b/open_instruct/events.out.tfevents.1694499102.g3041.70110.0
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4677f0734a8c0a6b9fc733e6e820c7a92da2674e0d495347bc7833151c0fbb83
+size 20187
--- a/open_instruct/events.out.tfevents.1694517340.g3043.20410.0
+++ b/open_instruct/events.out.tfevents.1694517340.g3043.20410.0
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:84c44ce55fde51eb2a2652665577f7cda24d784503bbb1d92e17ffea0031bc85
+size 189
--- a/open_instruct/events.out.tfevents.1694518076.g3043.23771.0
+++ b/open_instruct/events.out.tfevents.1694518076.g3043.23771.0
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4e424e6dffbff8270f4a58b9664c65383e3af16612cbee5332b7c6fa0dea63a6
+size 88
--- a/open_instruct/events.out.tfevents.1694518380.g3043.25749.0
+++ b/open_instruct/events.out.tfevents.1694518380.g3043.25749.0
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:94a1b7333712f79560c5d9cca5ccee9ca81c97fe377e6e7b8a20cc5c42a876ef
+size 15137
--- a/pytorch_model-00001-of-00002.bin
+++ b/pytorch_model-00001-of-00002.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7bf5c126225ef41a3047f4d08db5a3df4b9f571d719d7f99d76389746453259a
+size 9976628314
--- a/pytorch_model-00002-of-00002.bin
+++ b/pytorch_model-00002-of-00002.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d00215cd10c330608551ea333ce2184d1c77e2634cc2fd74ce539bf547b45c72
+size 3500318979
--- a/pytorch_model.bin.index.json
+++ b/pytorch_model.bin.index.json
@@ -0,0 +1,298 @@
+{
+  "metadata": {
+    "total_size": 13476847616
+  },
+  "weight_map": {
+    "lm_head.weight": "pytorch_model-00002-of-00002.bin",
+    "model.embed_tokens.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.0.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.0.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.0.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.0.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.1.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.1.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.1.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.1.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.1.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.1.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.1.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.1.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.10.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.10.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.10.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.10.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.10.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.10.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.10.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.10.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.10.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.11.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.11.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.11.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.11.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.11.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.11.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.11.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.11.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.11.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.12.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.12.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.12.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.12.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.12.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.12.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.12.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.12.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.12.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.13.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.13.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.13.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.13.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.13.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.13.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.13.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.13.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.13.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.14.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.14.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.14.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.14.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.14.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.14.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.14.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.14.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.14.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.15.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.15.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.15.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.15.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.15.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.15.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.15.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.15.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.15.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.16.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.16.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.16.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.16.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.16.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.16.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.16.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.16.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.16.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.17.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.17.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.17.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.17.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.17.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.17.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.17.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.17.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.17.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.18.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.18.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.18.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.18.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.18.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.18.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.18.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.18.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.18.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.19.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.19.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.19.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.19.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.19.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.19.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.19.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.19.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.19.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.2.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.2.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.2.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.2.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.2.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.2.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.2.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.2.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.2.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.20.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.20.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.20.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.20.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.20.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.20.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.20.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.20.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.20.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.21.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.21.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.21.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.21.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.21.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.21.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.21.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.21.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.21.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.22.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.22.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.22.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.22.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.22.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.22.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.22.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.22.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.22.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.23.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.23.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.23.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.23.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.23.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.23.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.23.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.23.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.23.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.24.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.24.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.24.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.24.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.24.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.24.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.24.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.24.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.24.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.25.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.25.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.25.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.25.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.25.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.25.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.25.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.25.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.25.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.26.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.26.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.26.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.26.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.26.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.26.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.26.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.26.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.26.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.27.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.27.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.27.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.27.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.27.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.27.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.27.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.27.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.27.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.28.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.28.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.28.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.28.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.28.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.28.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.28.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.28.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.28.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.29.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.29.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.29.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.29.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.29.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.29.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.29.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.29.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.29.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.3.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.3.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.3.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.3.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.3.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.3.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.3.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.3.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.3.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.30.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.30.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.30.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.30.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.30.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.30.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.30.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.30.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.30.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.31.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.31.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.31.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.31.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.31.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.31.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.31.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.31.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.31.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.4.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.4.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.4.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.4.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.4.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.4.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.4.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.4.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.4.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.5.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.5.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.5.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.5.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.5.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.5.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.5.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.5.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.5.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.6.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.6.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.6.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.6.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.6.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.6.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.6.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.6.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.6.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.7.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.7.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.7.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.7.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.7.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.7.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.7.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.7.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.7.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.8.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.8.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.8.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.8.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.8.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.8.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.8.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.8.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.8.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.9.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.9.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.9.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.9.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.9.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.9.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.9.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.9.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.9.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.norm.weight": "pytorch_model-00002-of-00002.bin"
+  }
+}
--- a/special_tokens_map.json
+++ b/special_tokens_map.json
@@ -0,0 +1,6 @@
+{
+  "bos_token": "<s>",
+  "eos_token": "</s>",
+  "pad_token": "<pad>",
+  "unk_token": "<unk>"
+}
--- a/tokenizer.model
+++ b/tokenizer.model
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
+size 499723
--- a/tokenizer_config.json
+++ b/tokenizer_config.json
@@ -0,0 +1,35 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "bos_token": {
+    "__type": "AddedToken",
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "clean_up_tokenization_spaces": false,
+  "eos_token": {
+    "__type": "AddedToken",
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "legacy": false,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": null,
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": {
+    "__type": "AddedToken",
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}